onboard

Automate developer onboarding by profiling environments and writing ~/.understudy/profile.json.

10|5|Updated Jun 3, 2026

Search Tags:#onboarding #interactive #profiling #profile #local-first #ml-tooling #open-model

Ready to run

npx skills add https://github.com/understudylabs/understudy-agent-tools --skill onboard-understudylabs

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: onboard
Source: https://github.com/understudylabs/understudy-agent-tools/tree/main/skills/onboard
Command: npx skills add https://github.com/understudylabs/understudy-agent-tools --skill onboard-understudylabs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Onboarding is streamlined by automating the first-run setup, including a background model download, machine profiling, ML tooling detection, and an interactive interview, resulting in a durable ~/.understudy/profile.json that future skills can reference and adapt to the user.

Core Features & Use Cases

Interactive, background-driven onboarding that profiles the machine, detects ML tooling, and gauges the user's goals.
Writes and keeps up-to-date the durable ~/.understudy/profile.json, plus the agent-card and history relevant to tailoring subsequent workflows.
Hands off to the understudy orchestrator to coordinate the flow of onboarding into the broader workflow.

Quick Start

Run the onboarding flow after installing the Understudy plugin to create your local profile and begin guided setup.

Frequently Asked Questions about onboard

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate developer onboarding with local machine profiling and ML tooling detection?▼

Developer onboarding is automated by running a guided interview that profiles your local environment, detects ML tooling, and writes a durable profile to ~/.understudy/profile.json. This configures subsequent skills to adapt to your machine and goals.

What is local-first onboarding for ML environments?▼

Local-first onboarding is a first-run setup process that downloads a small open-model, profiles your machine, and detects ML tooling locally. It creates a durable profile.json file that tailors future workflows without relying on external cloud services.

Do I need a specific local environment for ML tooling detection and open-model setup?▼

ML tooling detection and open-model setup require a local environment capable of downloading a small open model. The onboarding process verifies this readiness before proceeding with environment profiling and the guided interview.

How do I set up a durable local profile for tailoring ML workflows?▼

To set up a durable local profile, run the onboarding flow after installing the Understudy plugin. It writes your machine profile, agent-card, and goals to ~/.understudy/profile.json, which future skills reference to adapt their workflows.

What is the best way to kick off first-run setup for local ML model readiness?▼

The best way to kick off first-run setup is to run the onboarding flow, which handles background model download, machine profiling, and tooling detection automatically. It hands off to the orchestrator to coordinate the broader workflow setup.

Why does onboarding write a profile to ~/.understudy/profile.json?▼

Onboarding writes to ~/.understudy/profile.json to store a durable record of your environment profile, ML tooling, and interview goals. This allows subsequent skills to reference and automatically adapt their behavior to your specific setup.